{"id":"https://openalex.org/W4372349774","doi":"https://doi.org/10.1109/icassp49357.2023.10095204","title":"Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion","display_name":"Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349774","doi":"https://doi.org/10.1109/icassp49357.2023.10095204"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Strohman","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001306222"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.5685,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84634412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8140536546707153},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7166095972061157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6662940979003906},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6610304117202759},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6333116888999939},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.613349199295044},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5950201749801636},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5674659609794617},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.548922598361969},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5149641633033752},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5041278600692749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4847399890422821},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4576283097267151},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4472794532775879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4369688034057617},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.43427878618240356},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.42309603095054626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09152677655220032},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06997224688529968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140536546707153},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7166095972061157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6662940979003906},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6610304117202759},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6333116888999939},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.613349199295044},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5950201749801636},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5674659609794617},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.548922598361969},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5149641633033752},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5041278600692749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4847399890422821},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4576283097267151},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4472794532775879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4369688034057617},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.43427878618240356},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.42309603095054626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09152677655220032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06997224688529968},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2121879602","https://openalex.org/W2170653751","https://openalex.org/W2597655663","https://openalex.org/W2617258110","https://openalex.org/W2886025712","https://openalex.org/W2886319145","https://openalex.org/W2896457183","https://openalex.org/W2928941594","https://openalex.org/W2949197413","https://openalex.org/W2962745521","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2964346351","https://openalex.org/W2970641574","https://openalex.org/W2981532039","https://openalex.org/W3007227084","https://openalex.org/W3008181812","https://openalex.org/W3015383801","https://openalex.org/W3015760975","https://openalex.org/W3015995734","https://openalex.org/W3028545098","https://openalex.org/W3093501662","https://openalex.org/W3095311338","https://openalex.org/W3105816068","https://openalex.org/W3163300396","https://openalex.org/W3163907627","https://openalex.org/W3197898596","https://openalex.org/W3197976839","https://openalex.org/W3198442913","https://openalex.org/W4221151615","https://openalex.org/W4224137820","https://openalex.org/W4224457787","https://openalex.org/W4226420874","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6728881024","https://openalex.org/W6735377749","https://openalex.org/W6739901393","https://openalex.org/W6760633627","https://openalex.org/W6767552790"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W2529301793","https://openalex.org/W4237547500","https://openalex.org/W2384121599","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W2038083449","https://openalex.org/W4239268388","https://openalex.org/W2562096895"],"abstract_inverted_index":{"Typical":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"systems":[5],"are":[6],"built":[7],"to":[8,66],"recognize":[9],"independent":[10],"utterances":[11,22],"without":[12],"using":[13,85],"the":[14,18,28,43,48,51,68,72,77,81,86,91,105],"cross-utterance":[15],"context.":[16],"However,":[17],"context":[19,45,69],"over":[20],"multiple":[21],"often":[23],"provides":[24],"useful":[25],"information":[26],"for":[27],"ASR":[29,39,101],"task.":[30],"In":[31],"this":[32],"work,":[33],"we":[34],"propose":[35,59],"a":[36,60,98],"context-aware":[37],"end-to-end":[38],"model":[40],"that":[41,104],"injects":[42],"self-attentive":[44],"embedding":[46,70],"into":[47],"decoder":[49],"of":[50],"recurrent":[52],"neural":[53],"network":[54,88],"transducer":[55],"(RNN-T).":[56],"We":[57],"also":[58],"factorised":[61],"3-way":[62],"tensor":[63],"fusion":[64],"approach":[65,107],"fuse":[67],"with":[71],"acoustic":[73,78],"representations":[74,83],"extracted":[75],"from":[76],"encoder":[79],"and":[80],"text":[82],"obtained":[84],"prediction":[87],"based":[89],"on":[90,97],"previous":[92],"subword":[93],"units.":[94],"Experimental":[95],"results":[96],"long-form":[99],"Youtube":[100],"task":[102],"shows":[103],"proposed":[106],"achieves":[108],"10.8%":[109],"relative":[110],"word":[111],"error":[112],"rate":[113],"reductions.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}